Instructions to use mollysama/rwkv-mobile-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mollysama/rwkv-mobile-models with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mollysama/rwkv-mobile-models",
	filename="demos/translate/RWKV_v7_G1_0.4B_Translate_ctx4096_20250721_latest-Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use mollysama/rwkv-mobile-models with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mollysama/rwkv-mobile-models:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mollysama/rwkv-mobile-models:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mollysama/rwkv-mobile-models:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mollysama/rwkv-mobile-models:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf mollysama/rwkv-mobile-models:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mollysama/rwkv-mobile-models:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf mollysama/rwkv-mobile-models:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mollysama/rwkv-mobile-models:Q4_K_M

Use Docker

docker model run hf.co/mollysama/rwkv-mobile-models:Q4_K_M

LM Studio
Jan
Ollama
How to use mollysama/rwkv-mobile-models with Ollama:
```
ollama run hf.co/mollysama/rwkv-mobile-models:Q4_K_M
```

Unsloth Studio

How to use mollysama/rwkv-mobile-models with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mollysama/rwkv-mobile-models to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mollysama/rwkv-mobile-models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mollysama/rwkv-mobile-models to start chatting

Docker Model Runner
How to use mollysama/rwkv-mobile-models with Docker Model Runner:
```
docker model run hf.co/mollysama/rwkv-mobile-models:Q4_K_M
```

Lemonade

How to use mollysama/rwkv-mobile-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mollysama/rwkv-mobile-models:Q4_K_M

Run and chat with the model

lemonade run user.rwkv-mobile-models-Q4_K_M

List all available models

lemonade list

Upload 3 files

by Alic-Li - opened Sep 17, 2025

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

+12

-0

Files changed (4) hide show

.gitattributes +3 -0
WebRWKV/RWKV_v7_G1a_0.4B_Translate_ctx4096_20250915_latest.st +3 -0
WebRWKV/RWKV_v7_G1a_0.4B_Translate_ctx4096_20250915_latest_int8.prefab +3 -0
WebRWKV/RWKV_v7_G1a_0.4B_Translate_ctx4096_20250915_latest_nf4.prefab +3 -0

.gitattributes CHANGED Viewed

@@ -163,3 +163,6 @@ gguf/rwkv7-g1a-0.4b-20250905-ctx4096-Q8_0.gguf filter=lfs diff=lfs merge=lfs -te
 WebRWKV/rwkv7-g1a-0.4b-20250905-ctx4096-int8.prefab filter=lfs diff=lfs merge=lfs -text
 multimodal/model/modrwkv-v2-vision-adapter-0.4b-250915-f16.gguf filter=lfs diff=lfs merge=lfs -text
 multimodal/model/modrwkv-v2-0.4b-250915-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

 WebRWKV/rwkv7-g1a-0.4b-20250905-ctx4096-int8.prefab filter=lfs diff=lfs merge=lfs -text
 multimodal/model/modrwkv-v2-vision-adapter-0.4b-250915-f16.gguf filter=lfs diff=lfs merge=lfs -text
 multimodal/model/modrwkv-v2-0.4b-250915-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+WebRWKV/RWKV_v7_G1a_0.4B_Translate_ctx4096_20250915_latest_int8.prefab filter=lfs diff=lfs merge=lfs -text
+WebRWKV/RWKV_v7_G1a_0.4B_Translate_ctx4096_20250915_latest_nf4.prefab filter=lfs diff=lfs merge=lfs -text
+WebRWKV/RWKV_v7_G1a_0.4B_Translate_ctx4096_20250915_latest.st filter=lfs diff=lfs merge=lfs -text

WebRWKV/RWKV_v7_G1a_0.4B_Translate_ctx4096_20250915_latest.st ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0e4d4995bb2c732c58e12ddf5aa39e9d6391419bba3addfeaa92a91892a78415
+size 901742584

WebRWKV/RWKV_v7_G1a_0.4B_Translate_ctx4096_20250915_latest_int8.prefab ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:607bb1fec6ccda6d68d78ad07b85d3d916c77f0a29af4762beed8e074fe9fa0f
+size 621465077

WebRWKV/RWKV_v7_G1a_0.4B_Translate_ctx4096_20250915_latest_nf4.prefab ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:66ceed929a8a961901129514302bea5e7b8f2e1c2e2da2f3fff7c44ac0c06c5a
+size 476773181